{"title":"代理社会:融合现实世界的骨架和大型语言模型的纹理","authors":"Yuqi Bai, Kun Sun, Huishi Yin","doi":"arxiv-2409.10550","DOIUrl":null,"url":null,"abstract":"Recent advancements in large language models (LLMs) and agent technologies\noffer promising solutions to the simulation of social science experiments, but\nthe availability of data of real-world population required by many of them\nstill poses as a major challenge. This paper explores a novel framework that\nleverages census data and LLMs to generate virtual populations, significantly\nreducing resource requirements and bypassing privacy compliance issues\nassociated with real-world data, while keeping a statistical truthfulness.\nDrawing on real-world census data, our approach first generates a persona that\nreflects demographic characteristics of the population. We then employ LLMs to\nenrich these personas with intricate details, using techniques akin to those in\nimage generative models but applied to textual data. Additionally, we propose a\nframework for the evaluation of the feasibility of our method with respect to\ncapability of LLMs based on personality trait tests, specifically the Big Five\nmodel, which also enhances the depth and realism of the generated personas.\nThrough preliminary experiments and analysis, we demonstrate that our method\nproduces personas with variability essential for simulating diverse human\nbehaviors in social science experiments. But the evaluation result shows that\nonly weak sign of statistical truthfulness can be produced due to limited\ncapability of current LLMs. Insights from our study also highlight the tension\nwithin LLMs between aligning with human values and reflecting real-world\ncomplexities. Thorough and rigorous test call for further research. Our codes\nare released at https://github.com/baiyuqi/agentic-society.git","PeriodicalId":501112,"journal":{"name":"arXiv - CS - Computers and Society","volume":"8 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Agentic Society: Merging skeleton from real world and texture from Large Language Model\",\"authors\":\"Yuqi Bai, Kun Sun, Huishi Yin\",\"doi\":\"arxiv-2409.10550\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent advancements in large language models (LLMs) and agent technologies\\noffer promising solutions to the simulation of social science experiments, but\\nthe availability of data of real-world population required by many of them\\nstill poses as a major challenge. This paper explores a novel framework that\\nleverages census data and LLMs to generate virtual populations, significantly\\nreducing resource requirements and bypassing privacy compliance issues\\nassociated with real-world data, while keeping a statistical truthfulness.\\nDrawing on real-world census data, our approach first generates a persona that\\nreflects demographic characteristics of the population. We then employ LLMs to\\nenrich these personas with intricate details, using techniques akin to those in\\nimage generative models but applied to textual data. Additionally, we propose a\\nframework for the evaluation of the feasibility of our method with respect to\\ncapability of LLMs based on personality trait tests, specifically the Big Five\\nmodel, which also enhances the depth and realism of the generated personas.\\nThrough preliminary experiments and analysis, we demonstrate that our method\\nproduces personas with variability essential for simulating diverse human\\nbehaviors in social science experiments. But the evaluation result shows that\\nonly weak sign of statistical truthfulness can be produced due to limited\\ncapability of current LLMs. Insights from our study also highlight the tension\\nwithin LLMs between aligning with human values and reflecting real-world\\ncomplexities. Thorough and rigorous test call for further research. Our codes\\nare released at https://github.com/baiyuqi/agentic-society.git\",\"PeriodicalId\":501112,\"journal\":{\"name\":\"arXiv - CS - Computers and Society\",\"volume\":\"8 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computers and Society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.10550\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computers and Society","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.10550","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Agentic Society: Merging skeleton from real world and texture from Large Language Model
Recent advancements in large language models (LLMs) and agent technologies
offer promising solutions to the simulation of social science experiments, but
the availability of data of real-world population required by many of them
still poses as a major challenge. This paper explores a novel framework that
leverages census data and LLMs to generate virtual populations, significantly
reducing resource requirements and bypassing privacy compliance issues
associated with real-world data, while keeping a statistical truthfulness.
Drawing on real-world census data, our approach first generates a persona that
reflects demographic characteristics of the population. We then employ LLMs to
enrich these personas with intricate details, using techniques akin to those in
image generative models but applied to textual data. Additionally, we propose a
framework for the evaluation of the feasibility of our method with respect to
capability of LLMs based on personality trait tests, specifically the Big Five
model, which also enhances the depth and realism of the generated personas.
Through preliminary experiments and analysis, we demonstrate that our method
produces personas with variability essential for simulating diverse human
behaviors in social science experiments. But the evaluation result shows that
only weak sign of statistical truthfulness can be produced due to limited
capability of current LLMs. Insights from our study also highlight the tension
within LLMs between aligning with human values and reflecting real-world
complexities. Thorough and rigorous test call for further research. Our codes
are released at https://github.com/baiyuqi/agentic-society.git